WO2022257357A1 - Online car-hailing information processing method and apparatus, and device and computer storage medium - Google Patents

Abstract

Provided are an online car-hailing information processing method and apparatus, and a device and a computer storage medium, which relate to big data computing and deep learning technology in the technical field of artificial intelligence. The specific implementation scheme is: acquiring an online car-hailing query condition sent by a client, wherein the query condition comprises information of a starting place and a destination (201); determining a query time interval according to the query condition (202); for each moment within the query time interval, separately computing cost information of departing at each moment to the destination (203); according to the cost information of departing at each moment to the destination, determining a moment that meets the query condition as a recommended departure moment (204); determining a recommended order sending moment by using the recommended departure moment (205); and returning a query result to the client, wherein the query result comprises the recommended order sending moment, or, the query result comprises the recommended order sending moment and the cost information corresponding to the recommended order sending moment (206). By means of the method, a user can conveniently select an order sending time when the cost is lower, thereby improving the user experience, saving on network resources, and reducing the influence thereof on the system performance.

Description

Online car-hailing information processing method, device, equipment and computer storage medium

This application claims the priority of a Chinese patent application with an application date of June 07, 2021 and an application number of 202110633451.9 titled "Network car-hailing information processing method, device, equipment, and computer storage medium".

technical field

The present disclosure relates to the field of computer application technology, in particular to big data calculation and deep learning technology in artificial intelligence technology.

Background technique

With the development of the mobile Internet, the emergence of online car-hailing platforms has greatly changed people's lives. The online car-hailing platform puts drivers who need to receive orders and passengers who need to take taxis on one network platform. When a passenger places an order (subsequently referred to as "bill issuance"), the online car-hailing platform can effectively match drivers who are within a certain distance from the passenger, and the driver who is successfully matched will accept the order and drive the passenger to the destination specified in the order. land. The advantages of online car-hailing are departure at any time, high efficiency and no need to consider parking issues.

Passengers will inevitably consider the cost of online car-hailing in actual scenarios. For example, the current online car-hailing client will give the user an estimate of the cost of a taxi at the current moment after the passenger enters the origin and destination for the passenger's reference. But passengers can only consider whether to take a taxi based on this. If the current taxi fare is high due to road conditions or other problems, the passenger will give up taking a taxi or try to obtain the estimated taxi fare after a period of time. This will inevitably bring inconvenience to passengers, low efficiency, and users have tried to estimate the taxi fare many times, which also wastes network resources and puts pressure on system performance.

Contents of the invention

In view of this, the present disclosure provides a method, device, device, and computer storage medium for online car-hailing information processing, which facilitates users to choose a less costly billing time, improves user efficiency and experience, saves network resources, and reduces the impact on system performance. bring pressure.

According to the first aspect of the present disclosure, a method for processing online car-hailing information is provided, including:

Obtain the network car-hailing query condition sent by the client, and the query condition includes origin and destination information;

determining the query time interval according to the query condition;

For each moment in the query time interval, calculate the cost information starting from each moment and arriving at the destination;

Determining the time that satisfies the query condition as the recommended departure time according to the cost information from each time to the destination;

Using the recommended departure time to determine the recommended billing time;

A query result is returned to the client, the query result includes the recommended billing time, or the query result includes the recommended billing time and cost information corresponding to the recommended billing time.

According to a second aspect of the present disclosure, a method for processing online car-hailing information is provided, including:

Obtain the online car-hailing query conditions input by the user, and the query conditions include origin and destination information;

Send the query condition to the server, and obtain the query result returned by the server, the query result includes the recommended billing time, or the query result includes the recommended billing time and the cost information corresponding to the recommended billing time ;

Display the query results.

According to a third aspect of the present disclosure, an online car-hailing information processing device is provided, including:

The condition receiving unit is used to obtain the online car-hailing query condition sent by the client, and the query condition includes origin and destination information;

an interval determining unit, configured to determine the query time interval according to the query condition;

A cost calculation unit, configured to calculate the cost information starting from each time and arriving at the destination for each time in the query time interval;

The first recommendation unit is configured to determine the time that satisfies the query condition as the recommended departure time according to the cost information from each time to the destination;

The second recommending unit is configured to use the recommended departure time to determine the recommended billing time;

A result returning unit, configured to return a query result to the client, the query result includes the recommended billing time, or the query result includes the recommended billing time and the price corresponding to the recommended billing time information.

According to a fourth aspect of the present disclosure, an online car-hailing information processing device is provided, including:

A condition obtaining unit is used to obtain the network car-hailing query condition input by the user, and the query condition includes origin and destination information;

The server interaction unit is configured to send the query condition to the server, and obtain the query result returned by the server, the query result includes the recommended billing time, or the query result includes the recommended billing time and the recommended The price information corresponding to the time when the order is issued;

The result display unit is used to display the query result.

According to a fifth aspect of the present disclosure, there is provided an electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, the instructions are executed by the at least one processor to enable the at least one processor to perform the method as described above.

According to a sixth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute the above method.

According to a seventh aspect of the present disclosure, a computer program product comprises a computer program which, when executed by a processor, implements the method as described above.

It should be understood that what is described in this section is not intended to identify key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will be readily understood through the following description.

Description of drawings

The accompanying drawings are used to better understand the present solution, and do not constitute a limitation to the present disclosure. in:

FIG. 1 shows an exemplary system architecture to which embodiments of the present disclosure can be applied;

FIG. 2 is a flow chart of a method for processing online car-hailing information provided by an embodiment of the present disclosure;

FIG. 3 is a flowchart of a method for estimating the pick-up time provided by an embodiment of the present disclosure;

FIG. 4 is a flow chart of a method for estimating order receiving time provided by an embodiment of the present disclosure;

FIG. 5 is a schematic diagram of a pick-up time estimation model provided by an embodiment of the present disclosure;

FIG. 6 is a schematic diagram of an order receiving time estimation model provided by an embodiment of the present disclosure;

FIG. 7 is a schematic diagram of multi-task training provided by an embodiment of the present disclosure;

FIG. 8 is a flowchart of another online car-hailing information processing method provided by an embodiment of the present disclosure;

FIG. 9 is an example diagram of an interface displaying query results provided by an embodiment of the present disclosure;

FIG. 10 is a structural diagram of an online car-hailing information processing device provided by an embodiment of the present disclosure;

FIG. 11 is a schematic structural diagram of another online car-hailing information processing device provided by an embodiment of the present disclosure;

FIG. 12 is a block diagram of an electronic device used to implement an embodiment of the present disclosure.

Detailed ways

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

FIG. 1 shows an exemplary system architecture to which embodiments of the present disclosure can be applied.

As shown in FIG. 1 , the system architecture may include terminal devices 101 and 102 , a network 103 and a server 104 . The network 103 is used as a medium for providing communication links between the terminal devices 101 , 102 and the server 104 . Network 103 may include various connection types, such as wires, wireless communication links, or fiber optic cables, among others.

Users can use terminal devices 101 and 102 to interact with server 104 via network 103 . Terminal devices 101 and 102 can be installed with a client for online car-hailing applications or a client that can display information about online car-hailing, especially in this application, a client used by passengers is installed. Clients used by drivers may also be installed on other terminal devices.

Terminal devices 101 and 102 may be various mobile electronic devices. Including but not limited to smartphones, tablets, laptops, wearable devices, vehicle terminals, etc. An online car-hailing information processing device provided in the present application may be set and run in the above-mentioned server 104 . Another online car-hailing information processing device provided in this application can be set and run in the above-mentioned terminal devices 101 and 102 . It can be implemented as multiple software or software modules (for example, to provide distributed services), or can be implemented as a single software or software module, which is not specifically limited here.

The server 104 can be a single server, or a server group composed of multiple servers.

It should be understood that the numbers of terminal devices, networks and servers in Fig. 1 are only illustrative. According to the implementation needs, there can be any number of terminal devices, networks and servers.

In the existing online car-hailing service, the user can only choose whether to take a taxi now after inquiring about the cost information from the starting point to the destination, such as the price or the duration of the route. If the price is high due to factors such as road conditions, users may give up taking a taxi. However, the road conditions may improve in a short period of time, and users will lose the opportunity to improve the taxi-hailing experience later, which also inhibits the development of the online car-hailing industry. In some cases, many users choose to start now not because of the demand for the itinerary, but because they are worried that they will not be able to get a taxi due to the shortage of transportation, so they are anxious to queue up. This will increase the cost of taking a taxi during peak hours and make it more difficult to get a taxi. In view of this, the present disclosure provides a new idea, which can recommend the billing time for users, so that users who want to reduce the price or are not in a hurry to start now can choose to issue bills later according to the recommended billing time. The present disclosure will be described in detail below with reference to the embodiments.

Fig. 2 is a flow chart of a method for processing online car-hailing information provided by an embodiment of the present disclosure, and the method can be executed on the server side. As shown in Figure 2, the method includes the following steps:

In 201, the online car-hailing query condition sent by the client is acquired, and the query condition includes origin and destination information.

In 202, the query time interval is determined according to the query condition.

In 203, for each time in the query time interval, the cost information of departure from each time to the destination is calculated respectively.

In 204, according to the cost information from each time to the destination, the time that satisfies the query condition is determined as the recommended departure time.

In 205, the recommended departure time is used to determine the recommended billing time.

In 206, the query result is returned to the client, the query result includes the recommended billing time, or the query result includes the recommended billing time and the cost information corresponding to the recommended billing time.

It can be seen from the above technical solutions that this disclosure can determine the recommended billing time based on the cost information triggered at each time within the query time interval, and return the recommended billing time in the query result or further return the price corresponding to the recommended billing time information. It enables the user to select a less costly billing time based on the recommended billing time or further combining cost information. The first aspect avoids losing the taxi-hailing experience because the user finds that the departure cost at the current moment is too high. The second aspect also prevents users from frequently trying to inquire about the cost information of a taxi in a short period of time, which improves user efficiency and experience. The third aspect also reduces the cost of taxis for users, saving costs for users. The fourth aspect can also alleviate the problem of unreasonable capacity allocation caused by users concentrating on taxi-hailing peak hours. Fifthly, the user can obtain the billing time with a small cost at one time without multiple attempts, which saves network resources and reduces the impact on the system pressure. It can be said to serve multiple purposes.

Each step in the above embodiment will be described in detail below. Firstly, the above-mentioned step 201, that is, "obtaining the online car-hailing query condition sent by the client, where the query condition includes origin and destination information" is described in detail in conjunction with an embodiment.

The above online car-hailing query conditions are from the client, including at least origin and destination information. The origin information may be information input by the user, or may be obtained according to the current location of the client. Destination information is generally information input by a user. The "user" involved in this embodiment refers to the passenger who pre-uses the online car-hailing service.

Furthermore, in the present disclosure, the above query conditions may further include query time interval information, or further include a cost range.

The query time interval is usually a period of time in the future set by the user, such as within the next hour, within the next half hour, within the next two hours, etc., and is set according to the user's billing requirements. It reflects how long the user can accept to take a taxi. If the user is not in a hurry for the trip, a longer time interval can be set. If the user is in a hurry for the trip, a shorter time interval can be set.

The price range may be an acceptable taxi price set by the user. It can be reflected in the price range, for example, within 60 yuan. It can also be reflected in the length of the line, that is, the time-consuming range, for example, within 40 minutes. and many more.

The specific role of the above query time interval information and cost range will be reflected in the next steps.

The above-mentioned step 202, that is, "determining the query time interval according to the query condition" will be described in detail below in conjunction with an embodiment.

If the query condition includes the query time interval set by the user, the query time interval set by the user is directly used in this step, that is, the query time interval is determined from the query condition.

If the query condition does not include the query time interval set by the user, the default query time interval can be used in this step, for example, one hour in the future is set as the query time interval by default.

The above step 203, that is, "for each time in the query time interval, calculate the cost information from each time to the destination" will be described in detail below in conjunction with an embodiment.

In the present disclosure, the query time interval may be divided into various moments according to a preset granularity. The granularity may be a set fixed value, or a granularity corresponding to the length of the query time interval. For example, if the query time interval set by the user is half an hour, then the granularity is 1 minute. If the query time interval set by the user is 24 hours, the granularity is 10 minutes.

As one of the implementation methods, the following processing can be performed for each time in the query time interval, so as to obtain the cost information of departure and arrival at each time:

For time t _i , based on the road condition estimation results at time t _i , route planning is carried out for the origin and destination, and the estimated duration information of departure and arrival at the time t _i is obtained as the departure from time t _i Information about the cost of reaching the destination.

That is to say, firstly, the route planning is carried out from the starting point to the destination. During the route planning process, the road condition prediction method will be combined to predict the road condition at this time t _i , and the route planning will be carried out based on the road condition prediction result to obtain the time t _i Estimated time from departure to destination. Wherein, the method for route planning and traffic condition prediction may adopt any implementable manner, which is not limited in the present disclosure.

As another implementation, the following processing can be performed for each time in the query time interval, so as to obtain the cost information of departure and arrival at each time:

For time t _i , based on the estimated results of road conditions at time t _i , route planning is carried out for the origin and destination, and the length and estimated duration of the route from and to the destination at this time t _i are obtained. The pricing rule calculates the price, and takes the calculated price as the cost information from the moment to the destination.

Among them, the pricing rules for online car-hailing are usually relatively fixed, taking into account the interests of drivers, passengers and enterprises. Different regions or online car-hailing platforms will have some differences. The specific pricing rules can be pre-obtained and recorded from the online car-hailing platform.

Most of the online car-hailing pricing rules are composed of three aspects: starting price, mileage and duration. Generally speaking, the starting price includes a specific mileage and duration, such as 3 kilometers and 10 minutes. And when the driving mileage exceeds 3 kilometers, it will be accumulated at a certain rate per kilometer. When the driving time exceeds 10 minutes, it will be accumulated at a certain rate per minute. The result of the final sum is the calculated price. Since the driving time is related to the road conditions, the road conditions at different times are different, so the price of the same starting point and destination at different times may be different. This application does not limit the specific content of the online car-hailing pricing rules, and it is only illustrated here for the convenience of understanding.

The above step 204, that is, "determine the time that satisfies the query condition as the recommended departure time according to the cost information from each time to the destination" will be described in detail below in conjunction with an embodiment.

In this step, if the query condition includes the query time interval set by the user, then the N moments corresponding to the minimum cost in the query time interval can be used as the recommended departure time.

Since the cost information corresponding to each time in the query time interval has been determined in the above steps, the time with the lowest cost can be selected as the recommended departure time. The above N may be a preset positive integer.

If the query condition includes the price range set by the user, the time when the corresponding price in the query time interval meets the price range set by the user can be used as the recommended departure time. For example, if the user sets a price range within 40 yuan, the time below 40 yuan can be selected from the prices corresponding to each moment.

It should be noted that the recommended departure time determined in this step may be one or more than one.

Each step in the above embodiment will be described in detail below. Firstly, the above-mentioned step 205, that is, "determine the recommended billing time by using the recommended departure time" will be described in detail with reference to the embodiment.

The recommended departure time refers to the actual departure time of the recommended user, that is, the departure time from the starting point of the route. But for the user, it is more intuitive and necessary when to issue the order, therefore, it is necessary to determine the recommended time to issue the order.

As an achievable manner, the specific implementation process of this step may include the following steps:

Step S1: Use the recommended departure time to estimate the pick-up time of the online car-hailing car, and obtain the estimated order pick-up time.

Step S2: Estimate the order receiving time by using the estimated order receiving time, and obtain the recommended order issuing time.

From the user issuing the order to starting from the starting point of the route, there will be a process in which the online car-hailing driver receives the order and picks up the car. The so-called online car-hailing driver receiving order refers to the process that after the user sends the order, the online car-hailing platform sends the user's order to the matching online car-hailing driver, and then the online car-hailing driver accepts the order. The so-called pick-up refers to the process from the driver's location to the passenger's location after the online car-hailing driver accepts the order.

In the above step S1, the recommended departure time is used to invert the required pick-up time, so as to obtain the estimated order receiving time. The specific process is shown in Figure 3, including the following steps:

Step 301: Obtain a preset initial first duration.

The initial first duration may be a preset time unit, such as 1 minute.

Step 302: Determine the time of the first duration before the recommended departure time as the candidate order receiving time.

Assume that the recommended departure time is denoted as T _d , the time of the first duration before the recommended departure time is denoted as T _dn , and the candidate order receiving time at this time is T _dn .

Step 303: Estimate the pick-up time required for the candidate order pick-up time.

When estimating the pick-up time (denoted as T _pickup ) required for the candidate pick-up time T _dn in this step, a pick-up time estimation model can be used. The specific implementation will be described in detail later.

Step 304: Determine whether the estimated pick-up time is less than or equal to the first time, if yes, go to step 305; otherwise, go to step 306.

It is judged whether T _pickup is less than or equal to the current first duration, that is, whether T _dn +T _pickup ≤ T _d is judged.

Step 305: Determine the candidate order receiving time as the estimated order receiving time, and end the current estimation process.

In this case, the current T _dn is the estimated order receiving time T _t .

Step 306: Extend the first duration, and go to step 302 again.

In this case, the first duration can be extended, for example, by 1 minute, and the first duration becomes 2 minutes, and then go to step 302, and T _dn at this time is the time 2 minutes before T _d . By analogy, the above steps are carried out until the estimated order receiving time is determined.

In the above step S2, the estimated order receiving time is used to reverse the order receiving time, so as to obtain the recommended order issuing time. The specific process is shown in Figure 4, including the following steps:

Step 401: Obtain a preset initial second duration.

Similar to the initial first duration, the initial second duration may be a preset time unit, such as 1 minute.

Step 402: Determine the time of the second time period before the estimated order receiving time as the candidate order issuing time.

Since the estimated order receiving time is T _t , the second time before the estimated order receiving time is expressed as T _tm , and the candidate order issuing time at this time is T _tm .

Step 403: Estimate the order receiving time required for the candidate order issuing time.

When estimating the order receiving time (expressed as T _order ) required for the candidate order issuing time T _tm in this step, an order receiving time estimation model may be used. The specific implementation will be described in detail later.

Step 404: Determine whether the estimated order receiving time is less than or equal to the second time, if yes, go to step 405; otherwise, go to step 406.

It is judged whether T _order is less than or equal to the current second duration, that is, whether T _tm +T _order ≤ T _t is judged.

Step 405: Determine the candidate billing time as the recommended billing time, and end the current estimation process.

In this case, the current T _tm is the recommended billing time T _c .

Step 406: extend the second duration, and go to step 402 again.

In this case, the second duration can be extended, for example, by 1 minute, and the second duration becomes 2 minutes, and then go to step 402, where T _tm is 2 minutes before T _t . By analogy, the above steps are carried out until the recommended billing time is determined.

The above-mentioned pick-up time estimation model and order reception time estimation model will be described in detail below in conjunction with embodiments.

The above-mentioned pick-up time estimation model may adopt a regression model, which can output the corresponding pick-up time T _pickup when the candidate pick-up time T _dn is input.

As a preferred implementation, the structure of the pick-up time prediction model can be shown in FIG. 5 , which mainly includes an embedding layer and a fully connected layer. The embedding layer is mainly used to embed each feature of the input pick-up time estimation model, and obtain the vector representation of each feature respectively. The vector representation of each feature is input into the fully connected layer after fusion processing such as splicing, and the pick-up time is obtained by mapping the fully connected layer.

Among them, the features of the input pick-up duration estimation model include at least one of the user's location, destination, cost information at the recommended departure time, route length, weather information, and road condition information in addition to the candidate order receiving time T _dn , in Figure 5 to include all these information as an example. The cost information includes price and estimated duration as an example.

The above-mentioned order receiving time estimation model may also use a regression model, which can output the corresponding order receiving time T _order when the candidate order issuing time T _tm is input.

As a preferred implementation, the structure of the order receiving duration prediction model may be shown in FIG. 6 , which mainly includes an embedding layer and a fully connected layer. The embedding layer is mainly used to embed each feature of the input order time estimation model, and obtain the vector representation of each feature respectively. The vector representation of each feature is input into the fully connected layer after fusion processing such as splicing, and the order receiving time is obtained by mapping the fully connected layer.

Among them, in addition to the candidate order issuing time _Ttm , the features of the input order receiving time estimation model may also include at least one of the user's location, destination, cost information at the recommended departure time, route length, and weather information. In Figure 6, all these information are included as an example. The cost information includes price and estimated duration as an example.

In the above-mentioned pick-up time estimation model and order reception time estimation model, when the user's location and destination are embedded, the feature used may be POI information. POI information may include POI names, attributes, coordinate information, and the like. Embedding processing is actually a semantic representation of POI information. Since the POI name may have the characteristics of POI popularity and function, the POI name can be segmented and then vectorized. The attribute information of POI mainly adopts categories, such as public transport hubs, residential areas, etc., which can be represented by discrete values. The coordinate information describes the spatial heat information, so the entire area can be divided into cells and then serialized and numbered, and the number of the cell where the coordinates are located can be used as a feature representation.

Time features such as recommended departure time and candidate billing time can be represented by continuous values. For example, for a specific moment, it can include the hour value x, the minute value 12, and the second value z, and two characteristics can be defined

and

To represent, this representation can limit the value range to [-1,1].

For time features, discrete information such as whether it is a working day or a day of the week can also be used.

Price, estimated duration, and route length are all discrete values, which can be normalized and directly input into the model.

Weather features can be expressed discretely using onehot (one-hot) to express and distinguish weather such as sunny, cloudy, foggy, rainy (light rain, moderate rain, heavy rain, heavy rain), snow (light rain, moderate rain, heavy rain, heavy rain).

The road condition feature is introduced in the pick-up time estimation model because it has a high impact on the pick-up time, and the nearby road condition features are insufficiently expressed in other features. The characteristics of road conditions near the user mainly hope to describe the traffic flow density within a certain physical range. Therefore, neural networks such as CNN (Convolutional Neural Networks, convolutional neural network) and GCN (Graph Convolutional Network, graph convolutional neural network) can be used for encoding. For example, the user's location can be used as the center area to expand the preset range, such as 2km, to obtain a square area of 4km*4km, and then divide this area into 16 small areas of 1km*1km. The traffic flow characteristics in the area can be represented by the average value of road congestion coefficient weighted road length, for example:

Among them, I _x represents the traffic flow characteristics in the area, l _i represents the road length in the i-th small area, j _i represents the congestion coefficient of the i-th small area.

When pre-training the above-mentioned pick-up time estimation model, the training data used can be obtained from the logs of the online car-hailing platform. The online car-hailing platform records the time from when the driver receives the order to when the passenger boards the car, that is, the time of pick-up and driving. From this part of the data, the passenger's location, destination, price, route length, weather information, road condition information and the driver's order-taking time are extracted as Input, take the actual pick-up time as the target output, train the regression model to obtain the pick-up time estimation model. That is to say, when designing the loss function loss, the absolute value of the difference between the output of the pick-up time prediction model and the actual pick-up time is minimized.

When pre-training the above-mentioned order receiving time estimation model, the training data used can also be obtained from the logs of the online car-hailing platform. The online car-hailing platform records the time from when the passenger issued the order to when the driver received the order, that is, the time for receiving the order. From this part of the data, the location, destination, price, route length, weather information, and passenger issuing time are extracted as input, the actual order receiving time is taken as the target output, and the regression model is trained to obtain the order receiving time estimation model. That is to say, when designing the loss, minimize the absolute value of the difference between the output of the order receiving time prediction model and the actual order receiving time.

The above-mentioned pick-up time prediction model and order reception time prediction model can be trained separately, or can be trained by multi-task learning.

When performing multi-task learning training, as shown in Figure 7, the user's location, destination, estimated price, route length, and weather information are used as shared features, and the corresponding embedding processing part is a shared layer. The road condition feature is a unique feature of the pick-up time prediction model. The order receiving time is the input of the order receiving time estimation model. After the order receiving model outputs the order receiving time, the combination of the order receiving time and the order issuing time is the order receiving time, which is used as the input of the driving time estimation model. During multi-task training, a task can be randomly selected in each iteration, and after calculating the loss function of the task, the gradient descent method is used to update the model parameters corresponding to the task. Alternatively, a joint training method can also be used, that is, only the loss function of the driving task is used, and all model parameters are updated using the gradient descent method. Continue to iterate until the preset training end conditions are met, such as the loss function converges, or the number of iterations reaches the preset threshold of iterations, and so on.

FIG. 8 is a flow chart of another method for processing online car-hailing information provided by an embodiment of the present disclosure, and the method can be executed on a client. As shown in Figure 8, the method includes the following steps:

In 801, the online car-hailing query condition input by the user is acquired, and the query condition may include origin and destination information.

In the embodiment of the present disclosure, the client may be the client of the online car-hailing application, or the client of other applications integrated with the online car-hailing function, for example, the client of the map application integrated with the online car-hailing function.

The client terminal may provide the user with a first interface for the user to input the origin and destination information of the taxi.

Furthermore, a component for setting the query time interval or cost range can also be provided to the user. For example, an input box may be provided on the first interface for the user to input a query time interval or cost range. For another example, options such as a drop-down box may be provided on the first interface for the user to select and input a query time interval or cost range. The cost range may be a price range, or a time range of a route (that is, a taxi trip).

In 802, the query condition is sent to the server, and the query result returned by the server is obtained. The query result includes the recommended billing time, or the query result includes the recommended billing time and the cost information corresponding to the recommended billing time.

After the client sends the above query conditions to the server, the server executes the process in the embodiment shown in FIG. 2 to generate query results and return them to the client. The processing performed by the server side will not be repeated here.

Wherein, the cost information corresponding to the recommended billing time may include estimated duration information of departure and arrival at the time, or price information of departure and arrival at the time.

In 803, the query results are displayed.

The client terminal may provide the user with a second interface on which query results are displayed. At least one recommended billing time is displayed on the second interface, and there may be one or more recommended billing times. When displaying the recommended billing time, only the recommended billing time can be displayed, or each time in the query time interval can be displayed, but the recommended billing time among them can be highlighted.

While displaying the recommended billing time, the price information corresponding to the recommended billing time can be displayed. Only one type of cost information may be provided, or multiple types of cost information may be provided for the user to choose.

Fig. 9 is an example diagram showing a query result interface provided by an embodiment of the present disclosure. As shown in Fig. 9, two kinds of cost information can be provided for users to choose: according to the least cost (ie price) and according to time (ie line Estimated duration) minimum. When the user chooses to spend the least, the recommended billing time with the least cost will be displayed to the user. It is also possible to provide multiple online car-hailing platforms for users to choose to view. In Figure 9, taking the query time interval within one hour as an example, the recommended billing time is highlighted, that is, the time of 16:00, and the corresponding cost is 27 yuan.

Furthermore, a component for setting the departure time may be displayed on the second interface, for example, the "set departure time" component shown in FIG. 9 . After getting the event triggered by the component, record the departure time set by the user. When the departure time set by the user arrives or a preset time period before the departure time set by the user, a reminder message is displayed to the user.

Furthermore, a component for ordering and issuing bills may be displayed on the second interface, for example, the component of “reserving a taxi” shown in FIG. 9 . After obtaining the triggered event of the component, record the billing time set by the user; when the billing time set by the user is reached, send the online car-hailing order from the origin to the destination.

The above is a detailed description of the method provided by the present disclosure, and the device provided by the present disclosure will be described in detail below in conjunction with embodiments.

Fig. 10 is a structural diagram of an online car-hailing information processing device provided by an embodiment of the present disclosure, which is set on the server side. The device may be an application located on the server side, or may also be a functional unit such as a plug-in or a software development kit (Software Development Kit, SDK) in the application located on the server side. As shown in FIG. 10 , the apparatus 1000 may include: a condition receiving unit 1010 , an interval determining unit 1020 , a cost calculating unit 1030 , a first recommending unit 1040 , a second recommending unit 1050 and a result returning unit 1060 . The main functions of each component unit are as follows:

The condition receiving unit 1010 is used to obtain the online car-hailing query condition sent by the client, and the query condition includes origin and destination information.

The interval determining unit 1020 is configured to determine the query time interval according to the query condition.

The cost calculation unit 1030 is configured to calculate, for each time in the query time interval, the cost information from each time to the destination.

The first recommendation unit 1040 is configured to determine the time that satisfies the query condition as the recommended departure time according to the cost information from each time to the destination.

The second recommendation unit 1050 is configured to use the recommended departure time to determine the recommended billing time.

The result returning unit 1060 is configured to return a query result to the client. The query result includes the recommended billing time, or the query result includes the recommended billing time and the cost information corresponding to the recommended billing time.

As one of the implementation manners, the query condition also includes a query time interval, and the first recommendation unit 1040 is specifically configured to use the N times with the lowest corresponding costs within the query time interval as recommended departure times, where N is a preset positive integer.

As another implementation, the query condition also includes a cost range, and the first recommendation unit 1040 is specifically configured to use the time within the query time interval when the corresponding cost meets the cost range set by the user as the recommended departure time.

Wherein, the interval determining unit 1020 is specifically configured to: if the query condition includes the query time interval set by the user, adopt the query time interval set by the user; otherwise, adopt the default query time interval.

Wherein, the cost calculation unit 1030 is specifically configured to execute respectively for each moment:

Based on the road condition estimation result at this moment, carry out route planning for the origin and destination, and obtain the estimated duration information of departure and arrival at the destination at this moment as the cost information for departure and arrival at the destination at this moment; or,

Based on the estimated road conditions at this moment, route planning is carried out for the starting point and destination, and the length and estimated time of the route departing from and arriving at the destination at this moment are obtained, and the price is calculated using the online car-hailing pricing rules, and the calculated The price is used as the cost information from the moment to the destination.

Specifically, the second recommendation unit 1050 may include: a first prediction subunit 1051 and a second prediction subunit 1052 .

The first estimating subunit 1051 is used to estimate the pick-up time of the online car-hailing car by using the recommended departure time to obtain the estimated order receiving time;

The second estimating subunit 1052 is configured to use the estimated order receiving time to estimate the order receiving time to obtain the recommended order issuing time.

Wherein, the first estimation subunit 1051 is specifically used for:

According to the preset initial first time length, determine the time of the first time length before the recommended departure time as the candidate order receiving time;

Estimate the pick-up time required for the candidate pick-up time;

If the estimated pick-up time is less than or equal to the first time, determine the candidate pick-up time as the estimated pick-up time; otherwise, extend the first time, and switch to the time of the first time before the recommended departure time as the candidate pick-up time. single-moment operation.

As a preferred implementation, when the first estimating subunit 1051 estimates the pick-up time required for the candidate order-taking time, it specifically executes: combining the user's location, destination, cost information, route length, weather information and At least one of the road condition information and the candidate pick-up time are input into the pick-up time estimation model to obtain the pick-up time required for the candidate pick-up time.

Wherein, the second estimation subunit 1052 is specifically used for:

According to the preset initial second time period, determine the second time period before the estimated order receiving time as the candidate order issuing time;

Estimate the order receiving time required for the candidate order issuing time;

If the estimated order-receiving time is less than or equal to the second time-length, determine the candidate order-issuing time as the recommended order-issuing time, otherwise, extend the second time-length, and switch to the second time-long time before the estimated order-receiving time as the candidate The operation at the moment of billing.

As a preferred implementation manner, when the second estimating subunit 1052 estimates the order-receiving time required for the candidate order-issuing moment, it specifically performs: the user's location, destination, cost information, route length and weather information Input at least one of the candidate order-issuing times into the order-receiving time-duration estimation model to obtain the order-receiving time required for the candidate order-issuing time.

FIG. 11 is a schematic structural diagram of another online car-hailing information processing device provided by an embodiment of the present disclosure, which is set in a terminal device. The apparatus may be an application located in the terminal device, or may also be a functional unit such as a plug-in or a software development kit (Software Development Kit, SDK) located in the application of the terminal device. As shown in FIG. 11 , the device may include: a condition acquisition unit 1101 , a server interaction unit 1102 and a result presentation unit 1103 , and may further include a first component response unit 1104 and a second component response unit 1105 . The main functions of each component unit are as follows:

A condition acquisition unit 1101, configured to acquire the online car-hailing query condition input by the user, the query condition includes origin and destination information;

The server interaction unit 1102 is configured to send the query condition to the server, and obtain the query result returned by the server, the query result includes the recommended billing time, or the query result includes the recommended billing time and the cost information corresponding to the recommended billing time ;

A result display unit 1103, configured to display query results.

Wherein, the cost information corresponding to the recommended billing time may include: information on the estimated duration of departure and arrival at the destination at this time, or price information on departure and arrival at the destination at this time.

Furthermore, the result display unit 1103 can also be used to display a component for setting the departure time on the interface.

The first component response unit 1104 is configured to record the departure time set by the user after obtaining the event triggered by the component; trigger the result display unit when the departure time set by the user arrives or is preset before the departure time set by the user 1103 Display a reminder message to the user.

Furthermore, the result display unit 1103 is also used to display the component of ordering and billing on the interface.

The second component response unit 1105 is used to record the billing time set by the user after obtaining the event triggered by the component; Destination online car-hailing orders.

Each embodiment in this specification is described in a progressive manner, the same and similar parts of each embodiment can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, as for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for relevant parts, please refer to part of the description of the method embodiment.

According to the embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

As shown in FIG. 12 , it is a block diagram of an electronic device according to an online car-hailing information processing method according to an embodiment of the present disclosure. Electronic device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are by way of example only, and are not intended to limit implementations of the disclosure described and/or claimed herein.

As shown in FIG. 12 , the device 1200 includes a computing unit 1201 that can execute according to a computer program stored in a read-only memory (ROM) 1202 or loaded from a storage unit 1208 into a random-access memory (RAM) 1203. Various appropriate actions and treatments. In the RAM 1203, various programs and data necessary for the operation of the device 1200 can also be stored. The computing unit 1201, ROM 1202, and RAM 1203 are connected to each other through a bus 1204. An input/output (I/O) interface 1205 is also connected to the bus 1204 .

Multiple components in the device 1200 are connected to the I/O interface 1205, including: an input unit 1206, such as a keyboard, a mouse, etc.; an output unit 1207, such as various types of displays, speakers, etc.; a storage unit 1208, such as a magnetic disk, an optical disk, etc. ; and a communication unit 1209, such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 1209 allows the device 1200 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks.

The computing unit 1201 may be various general-purpose and/or special-purpose processing components with processing and computing capabilities. Some examples of computing units 1201 include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processing processor (DSP), and any suitable processor, controller, microcontroller, etc. The calculation unit 1201 executes the various methods and processes described above, such as the online car-hailing information processing method. For example, in some embodiments, the online car-hailing information processing method can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as the storage unit 1208 .

In some embodiments, part or all of the computer program may be loaded and/or installed on the device 1200 via the ROM 802 and/or the communication unit 1209. When the computer program is loaded into the RAM 1203 and executed by the computing unit 1201, one or more steps of the online car-hailing information processing method described above can be executed. Alternatively, in other embodiments, the computing unit 1201 may be configured in any other appropriate manner (for example, by means of firmware) to execute the online car-hailing information processing method.

Various implementations of the systems and techniques described herein can be implemented in digital electronic circuitry, systems integrated circuits, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips system (SOC), complex programmable logic device (CPLD), computer hardware, firmware, software, and/or a combination thereof. These various embodiments may include being implemented in one or more computer programs executable and/or interpreted on a programmable system including at least one programmable processor, the programmable processor Can be special-purpose or general-purpose programmable processor, can receive data and instruction from storage system, at least one input device, and at least one output device, and transmit data and instruction to this storage system, this at least one input device, and this at least one output device an output device.

Program codes for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, so that the program codes, when executed by the processor or controller, make the flow diagrams and/or block diagrams specified The function/operation is implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include one or more wire-based electrical connections, portable computer discs, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.

To provide for interaction with the user, the systems and techniques described herein can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user. ); and a keyboard and pointing device (eg, a mouse or a trackball) through which a user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and can be in any form (including Acoustic input, speech input or, tactile input) to receive input from the user.

The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., as a a user computer having a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system. The components of the system can be interconnected by any form or medium of digital data communication, eg, a communication network. Examples of communication networks include: Local Area Network (LAN), Wide Area Network (WAN) and the Internet.

A computer system may include clients and servers. Clients and servers are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the management problems existing in traditional physical host and virtual private server (VPs, Ⅵ irtual Private Server) services. Difficulty and weak business expansion. The server can also be a server of a distributed system, or a server combined with a blockchain.

It should be understood that steps may be reordered, added or deleted using the various forms of flow shown above. For example, each step described in the present application may be executed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution disclosed in the present disclosure can be achieved, no limitation is imposed herein.

The specific implementation manners described above do not limit the protection scope of the present disclosure. It should be apparent to those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made depending on design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present disclosure shall be included within the protection scope of the present disclosure.

Claims (30)

1. A method for processing online car-hailing information, comprising:

   Obtain the online car-hailing query condition sent by the client, the query condition includes origin and destination information;

   determining the query time interval according to the query condition;

   For each moment in the query time interval, calculate the cost information starting from each moment and arriving at the destination;

   Determining the time that satisfies the query condition as the recommended departure time according to the cost information from each time to the destination;

   Using the recommended departure time to determine the recommended billing time;

   A query result is returned to the client, the query result includes the recommended billing time, or the query result includes the recommended billing time and cost information corresponding to the recommended billing time.
2. The method according to claim 1, wherein the query condition further includes a query time interval;

   Determining the time that satisfies the query condition as the recommended departure time according to the cost information from each time to the destination includes: taking N times with the smallest corresponding costs in the query time interval as the recommended departure time, the N is a default positive integer.
3. The method according to claim 1, wherein the query condition further includes a cost range;

   The determining the time that satisfies the query condition as the recommended departure time according to the cost information from each time to the destination includes: taking the time when the corresponding cost in the query time interval meets the cost range set by the user as the recommended departure time time.
4. The method according to claim 1, wherein determining the query time interval according to the query condition comprises:

   If the query condition includes the query time interval set by the user, the query time interval set by the user is adopted; otherwise, the default query time interval is adopted.
5. The method according to claim 1, wherein said calculating the cost information starting from each moment and arriving at the destination respectively comprises:

   Execute separately for each time: based on the road condition estimation result at that time, carry out route planning for the origin and destination, and obtain the estimated duration information of departure and arrival at that time as the departure and arrival destination at that time or, based on the road condition estimation results at that moment, carry out route planning for the origin and destination, obtain the route length and estimated time from departure to destination at that moment, and use online car-hailing to calculate the price The rule calculates the price, and uses the calculated price as the cost information from the moment to the destination.
6. The method according to claim 1, wherein using the recommended departure time, determining the recommended billing time comprises:

   Estimate the pick-up time of the online car-hailing car by using the recommended departure time, and obtain the estimated time of receiving the order;

   The order receiving time is estimated by using the estimated order receiving time to obtain the recommended order issuing time.
7. The method according to claim 6, wherein, using the recommended departure time to estimate the pick-up time of the online car-hailing car, obtaining the estimated order receiving time includes:

   According to the preset initial first time length, determine the time of the first time length before the recommended departure time as the candidate order receiving time;

   Estimate the pick-up time required for the candidate order pick-up time;

   If the estimated pick-up time is less than or equal to the first time length, then determine the candidate order receiving time as the estimated order receiving time, otherwise, extend the first time length, and turn to the determination The step of recommending the time of the first time before the departure time as the candidate order receiving time.
8. The method according to claim 7, wherein estimating the pick-up time required for the candidate order-taking moment comprises:

   Inputting the user's location, destination, at least one of the cost information, route length, weather information, and road condition information, as well as the candidate order-receiving time into the pick-up duration estimation model, to obtain the candidate order-receiving time The required pick-up time.
9. The method according to claim 6, wherein, using the estimated order receiving time to estimate the order receiving time, and obtaining the recommended order issuing time includes:

   According to the preset initial second time length, determine the time of the second time length before the estimated order receiving time as the candidate order issuing time;

   Estimate the order receiving time required for the candidate order issuing time;

   If the estimated time for receiving orders is less than or equal to the second time, then determine the candidate time for issuing orders as the recommended time for issuing orders; The step of estimating the second time period before the order receiving time as the candidate order issuing time.
10. The method according to claim 9, wherein estimating the order receiving time required for the candidate order issuing moment comprises:

    Inputting the user's location, destination, at least one of the cost information, route length, and weather information, as well as the candidate billing time into the order receiving time estimation model, to obtain the time required for the candidate billing time Order time.
11. A method for processing online car-hailing information, comprising:

    Obtain the online car-hailing query conditions input by the user, and the query conditions include origin and destination information;

    Send the query condition to the server, and obtain the query result returned by the server, the query result includes the recommended billing time, or the query result includes the recommended billing time and the cost information corresponding to the recommended billing time ;

    Display the query results.
12. The method according to claim 11, wherein the cost information corresponding to the recommended billing time includes:

    Information about the estimated duration of departure and arrival at the destination at this time, or price information for departure and arrival at the destination at this time.
13. The method of claim 11, further comprising:

    Displaying a component for setting the departure time on the interface;

    After obtaining the event triggered by the component, record the departure time set by the user;

    When the departure time set by the user arrives or a preset time period before the departure time set by the user, a reminder message is displayed to the user.
14. The method of claim 11, further comprising:

    Displaying components for ordering and issuing bills on the interface;

    After obtaining the event triggered by the component, record the billing time set by the user;

    When the billing time set by the user is reached, the online car-hailing order from the origin to the destination is sent.
15. An online car-hailing information processing device, comprising:

    The condition receiving unit is used to obtain the online car-hailing query condition sent by the client, and the query condition includes origin and destination information;

    an interval determining unit, configured to determine the query time interval according to the query condition;

    A cost calculation unit, configured to calculate the cost information starting from each time and arriving at the destination for each time in the query time interval;

    The first recommendation unit is configured to determine the time that satisfies the query condition as the recommended departure time according to the cost information from each time to the destination;

    The second recommending unit is configured to use the recommended departure time to determine the recommended billing time;

    A result returning unit, configured to return a query result to the client, the query result includes the recommended billing time, or the query result includes the recommended billing time and the price corresponding to the recommended billing time information.
16. The device according to claim 15, wherein the query condition further includes a query time interval, and the first recommending unit is specifically configured to use the N times with the smallest corresponding costs within the query time interval as the recommended departure time, so N is a preset positive integer; or, the query condition also includes a cost range, and the first recommendation unit is specifically configured to use the time when the corresponding cost in the query time interval conforms to the cost range set by the user as a recommendation departure time.
17. The device according to claim 15, wherein the interval determining unit is specifically configured to: if the query condition includes the query time interval set by the user, then adopt the query time interval set by the user; otherwise, use the query time set by default interval.
18. The device according to claim 15, wherein the cost calculation unit is specifically configured to respectively execute at each moment:

    Based on the road condition estimation result at this moment, carry out route planning for the origin and destination, and obtain the estimated duration information of departure and arrival at this moment as the cost information of departure and arrival at this moment; or,

    Based on the estimated result of the road conditions at this moment, carry out route planning for the starting point and destination, obtain the route length and estimated duration of the departure and arrival destination at this moment, use the online car-hailing pricing rules to calculate the price, and calculate the The obtained price is used as the cost information from the moment to the destination.
19. The device according to claim 15, wherein the second recommending unit comprises:

    The first estimating subunit is used to estimate the pick-up time of the online car-hailing car by using the recommended departure time to obtain the estimated order receiving time;

    The second estimating subunit is configured to use the estimated order receiving time to estimate the order receiving time to obtain the recommended order issuing time.
20. The device according to claim 19, wherein the first estimation subunit is specifically configured to:

    According to the preset initial first time length, determine the time of the first time length before the recommended departure time as the candidate order receiving time;

    Estimate the pick-up time required for the candidate order pick-up time;

    If the estimated pick-up time is less than or equal to the first time length, then determine the candidate order receiving time as the estimated order receiving time, otherwise, extend the first time length, and turn to the determination The operation of recommending the first time before the departure time as the candidate order receiving time.
21. The device according to claim 20, wherein when the first estimating subunit is estimating the pick-up time required for the candidate order-taking moment, it specifically executes: combining the user's location, destination, At least one of the cost information, route length, weather information and road condition information and the candidate order receiving time are input into the pick-up time duration estimation model to obtain the pick-up time required for the candidate order receiving time.
22. The device according to claim 19, wherein the second estimating subunit is specifically configured to:

    According to the preset initial second time length, determine the time of the second time length before the estimated order receiving time as the candidate order issuing time;

    Estimate the order receiving time required for the candidate order issuing time;

    If the estimated order receiving time is less than or equal to the second time length, then determine the candidate order issuing time as the recommended order issuing time; otherwise, extend the second time length, and turn to the determination The second time before the estimated order receiving time is used as the candidate order issuing time.
23. The device according to claim 22, wherein, when the second estimating subunit estimates the order-receiving time required for the candidate order-issuing moment, it specifically executes: adding the user's location, destination, At least one of the cost information, route length and weather information and the candidate order issuing time are input into the order receiving time estimation model to obtain the order receiving time required for the candidate order issuing time.
24. An online car-hailing information processing device, comprising:

    A condition acquisition unit, configured to acquire the online car-hailing query condition input by the user, the query condition including origin and destination information;

    The server interaction unit is configured to send the query condition to the server, and obtain the query result returned by the server, the query result includes the recommended billing time, or the query result includes the recommended billing time and the recommended The price information corresponding to the time when the order is issued;

    The result display unit is used to display the query result.
25. The device according to claim 24, wherein the cost information corresponding to the recommended billing time includes:

    Information about the estimated duration of departure and arrival at the destination at this time, or price information for departure and arrival at the destination at this time.
26. The device according to claim 24, wherein the result display unit is further configured to display a component for setting a departure time on the interface;

    The device also includes: a first component response unit, configured to record the departure time set by the user after acquiring the triggered event of the component; when the departure time set by the user arrives or before the departure time set by the user For a preset duration, a reminder message is displayed to the user through the result display unit.
27. The device according to claim 24, wherein the result display unit is further configured to display an appointment billing component on the interface;

    The second component response unit is configured to record the billing time set by the user after obtaining the event triggered by the component; when the billing time set by the user is reached, send the The online car-hailing order from the origin to the destination.
28. An electronic device comprising:

    at least one processor; and

    a memory communicatively coupled to the at least one processor; wherein,

    The memory stores instructions executable by the at least one processor, the instructions are executed by the at least one processor, so that the at least one processor can perform any one of claims 1-14 Methods.
29. A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute the method according to any one of claims 1-14.
30. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-14.

Images